Neural Sign Actors: A diffusion model for 3D sign language production from text
This work addresses the problem of creating realistic sign language avatars to bridge communication gaps for Deaf and Hard of Hearing communities, representing an incremental improvement over existing methods.
The paper tackles the challenge of generating realistic 3D sign language motions from text by proposing a diffusion model trained on a large-scale dataset of 4D signing avatars, showing that it considerably outperforms previous methods in quantitative and qualitative experiments.
Sign Languages (SL) serve as the primary mode of communication for the Deaf and Hard of Hearing communities. Deep learning methods for SL recognition and translation have achieved promising results. However, Sign Language Production (SLP) poses a challenge as the generated motions must be realistic and have precise semantic meaning. Most SLP methods rely on 2D data, which hinders their realism. In this work, a diffusion-based SLP model is trained on a curated large-scale dataset of 4D signing avatars and their corresponding text transcripts. The proposed method can generate dynamic sequences of 3D avatars from an unconstrained domain of discourse using a diffusion process formed on a novel and anatomically informed graph neural network defined on the SMPL-X body skeleton. Through quantitative and qualitative experiments, we show that the proposed method considerably outperforms previous methods of SLP. This work makes an important step towards realistic neural sign avatars, bridging the communication gap between Deaf and hearing communities.